Large-scale simulations of plastic neural networks on neuromorphic hardware
- Submitting institution
-
The University of Manchester
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 50412465
- Type
- D - Journal article
- DOI
-
10.3389/fnana.2016.00037
- Title of journal
- Frontiers in Neuroanatomy
- Article number
- 37
- First page
- -
- Volume
- 10
- Issue
- 37
- ISSN
- 1662-5129
- Open access status
- Out of scope for open access requirements
- Month of publication
- April
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
A - Computer Science
- Citation count
- 13
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- "This paper documents the results of a long international collaboration under the auspices of the EU flagship Human Brain Project between the Manchester SpiNNaker team, KTH Stockholm, and the Zuse Institute, Berlin, to implement Bayesian Confidence Propagation Neural Network (BCPNN) learning rule on SpiNNaker.
This was the world''s largest plastic neural network ever simulated on power-efficient neuromorphic hardware - a comparable simulation on a Cray XC-30 supercomputer system required approximately 45× more power. The work underlines the unique flexibility that SpiNNaker gains, as a neuromorphic platform, from its use of software for neuron and synapse models, and for learning rules."
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
